Power grid fault simulation training system and method based on augmented reality

Abstract

The invention relates to the technical field of intelligent power grids, in particular to a power grid fault simulation training system and method based on augmented reality, and the system comprises a data collection module which is used for collecting the power grid fault simulation data of each power grid device; the data preprocessing module is used for preprocessing the power grid fault simulation data; the fault scene construction module is used for constructing a power grid fault simulation scene according to the actual power grid fault integration data; the simulation training interaction module is used for carrying out training interaction on power grid operation and maintenance personnel according to the virtual reality operation instruction and the fault information of each power grid device; and the risk assessment module is used for performing risk assessment on the operation state of the power grid according to the fault information. According to the invention, power grid fault simulation training can be carried out on power grid operation and maintenance personnel, risk assessment can be carried out on the power grid operation state, and the power grid fault simulation training effect and the power grid operation risk assessment accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of smart grids, and in particular to a grid fault simulation training system and method based on extended reality. Background Art

[0002] The power grid has the characteristics of dense line switches and many branches, which makes it difficult to accurately simulate fault conditions in power grid fault simulation training, thus affecting the training effect. Traditional fault simulation methods often repeatedly calculate fault risk scenarios with the same consequences during risk assessment, resulting in poor timeliness of fault risk assessment.

[0003] Chinese patent publication number CN102508081A discloses a distribution network fault simulation method, device and distribution network system, including: a dual-source power supply line for loading simulated load current and simulated fault current; a simulation protection module, communicating with the simulated power distribution master station through a first network port, executing a closing protection action according to a first remote control command sent by the simulated power distribution master station, and feeding back the execution action information to the simulated power distribution master station; multiple simulated power distribution terminal modules, communicating with the simulated power distribution master station through a second network port, reporting the detected simulated fault current to the simulated power distribution master station, executing the action of cutting off the simulated fault current according to a second remote control command sent by the simulated power distribution master station; and feeding back the execution action information to the simulated power distribution master station; a simulation fault recovery module, after cutting off the simulated fault current, controlling the switch to execute the closing action and restore power supply to the non-fault area. This solution cannot provide power grid fault simulation training for power grid operation and maintenance personnel and conduct risk assessment of power grid operation failures. Summary of the invention

[0004] To this end, the present invention provides a power grid fault simulation training system and method based on extended reality, so as to overcome the problems in the prior art of being unable to conduct power grid fault simulation training for power grid operation and maintenance personnel and to conduct risk assessment of power grid operation status, resulting in poor power grid fault simulation training effect and poor accuracy of power grid operation risk assessment.

[0005] To achieve the above objectives, on the one hand, the present invention provides a power grid fault simulation training system based on extended reality, the system comprising: A data acquisition module is used to collect power grid fault simulation data of each power grid device; A data preprocessing module, used for preprocessing the power grid fault simulation data to obtain actual power grid fault simulation data; A fault scenario construction module, used to integrate the actual power grid fault simulation data to obtain actual power grid fault integrated data, and also used to construct a power grid fault simulation scenario according to the actual power grid fault integrated data; A simulation training interaction module is used to simulate monitoring of the fault information of each power grid device according to the power grid fault simulation scenario to obtain a simulation monitoring result, and is also used to obtain simulation operation data according to the simulation monitoring result, and output virtual reality operation instructions according to the simulation operation data, and is also used to perform training interaction for power grid operation and maintenance personnel according to the virtual reality operation instructions and the fault information of each power grid device; The risk assessment module is used to perform risk assessment on the operation status of the power grid according to the fault information, and is also used to update the risk assessment process of the operation status of the power grid according to the load of the power grid.

[0006] Furthermore, the data preprocessing module performs outlier detection on the power grid fault simulation data of each power grid device according to the data anomaly detection algorithm to obtain corresponding data anomaly values, and processes the data anomaly values ​​according to the data anomaly value processing scheme corresponding to the power grid fault simulation data to obtain corresponding anomaly value processing results, and performs data conversion on the anomaly value processing results according to the data conversion scheme to obtain corresponding actual power grid fault simulation data.

[0007] Furthermore, the fault scenario construction module performs correlation analysis on the actual power grid fault simulation data corresponding to each power grid device with the power grid device data and the historical power grid fault data according to the correlation analysis algorithm to obtain an actual correlation ZX, and compares the actual correlation ZX with a preset correlation ZX0, performs an integrated judgment on the actual power grid fault simulation data of the power grid device according to the comparison result, and integrates the actual power grid fault simulation data of the power grid device according to the judgment result, wherein: When ZX≥ZX0, the fault scenario construction module determines to integrate the actual power grid fault simulation data of the power grid device, and integrates the actual power grid fault simulation data according to the default data integration rule of the power grid device to obtain the actual power grid fault integrated data; When ZX<ZX0, the fault scenario construction module determines not to integrate the actual power grid fault simulation data of the power grid device.

[0008] Furthermore, the fault scenario construction module trains the convolutional neural network model according to a preset power grid fault simulation scenario construction data set, outputs the convolutional neural network model that meets the preset accuracy as a power grid fault simulation scenario construction model, and inputs the actual power grid fault integrated data into the power grid fault simulation scenario construction model for construction to obtain a power grid fault simulation scenario.

[0009] Further, the simulation training interaction module obtains the fault type characteristic data G_i of each power grid device and the operating status data Y_i corresponding to each power grid device according to the power grid fault simulation scenario, and calculates the power grid fault index FZ_i corresponding to each power grid device according to the fault type characteristic data G_i and the operating status data Y_i, respectively, and sets FZ_i=a_i×G_i+b_i×Y_i, a_i represents the coefficient used to adjust the fault type characteristic data G_i, b_i represents the coefficient used to adjust the operating status data Y_i, and compares the power grid fault index FZ_i with the preset power grid fault index FZ0_i corresponding to each power grid device, and simulates monitoring of the fault information of each power grid device according to the comparison result, wherein: When FZ_i≥FZ0_i, the simulation training interaction module simulates monitoring of the fault information of the power grid equipment, and performs fault labeling on the fault information of the power grid equipment according to the preset power grid fault index corresponding to the power grid equipment, obtains the fault labeling result, and simulates monitoring of the fault labeling result through a data visualization method; When FZ_i<FZ0_i, the simulation training interaction module does not perform simulation monitoring on the fault information of the power grid equipment.

[0010] Furthermore, the simulation training interaction module identifies the simulation monitoring results according to the simulation operation data identification model to obtain simulation operation data, and compares the simulation operation data with the standard simulation operation data-virtual reality operation instruction template, and outputs the virtual reality operation instruction according to the comparison result, wherein: When there is preset standardized simulation operation data consistent with the simulation operation data in the standard simulation operation data-virtual reality operation instruction template, the preset virtual reality operation instruction corresponding to the preset standardized simulation operation data is output as the virtual reality operation instruction; When there is no preset standardized simulation operation data consistent with the simulation operation data in the standard simulation operation data-virtual reality operation instruction template, the virtual reality operation instruction is not output.

[0011] Furthermore, the simulation training interaction module calculates the similarity between the virtual reality operation instructions and the fault information of each power grid device according to the similarity measurement method, obtains the actual similarity A1 corresponding to each power grid device, and compares the actual similarity A1 with the preset similarity A0 of each power grid device, and performs training interaction for the power grid operation and maintenance personnel according to the comparison result, wherein: When A1<A0, the simulation training interaction module does not perform training interaction for the power grid operation and maintenance personnel; When A1≥A0, the simulation training interaction module sorts the actual similarity between the fault information of each power grid device satisfying A1≥A0 and the virtual reality operation instruction, and performs training interaction for the power grid operation and maintenance personnel according to the preset power grid fault handling solution corresponding to the largest actual similarity.

[0012] Furthermore, the risk assessment module collects the voltage data and current data in the fault information according to a preset collection time period, and sets the collected voltage data as a first time series , set the collected current data as the second time series ,in represents the voltage value at time m, Represents the current value at time n and creates a distance matrix Store the first time series To the second time series The distance between the points in ,in , , represents the voltage value at time k, represents the current value at time l; Build a The same cumulative distance matrix ,set up , and according to Cumulative distance matrix Calculate and use the cumulative distance matrix The best matching path Calculate and set , where P represents the backtracking path and r represents the cumulative distance matrix The index in and the best matching path The best matching path Compare and conduct risk assessment on the power grid operation status based on the comparison results, including: when > When , the risk assessment module assesses the power grid operation state as a high-risk operation state; when = When , the risk assessment module assesses the power grid operation state as a medium-risk operation state; when < When the risk assessment module assesses the power grid operation state as a low-risk operation state.

[0013] Furthermore, the risk assessment module calculates the grid load Q according to the unit power consumption index P and the unit quantity N, and sets The grid load Q is compared with the preset grid load Q0, the grid load characteristic type is judged according to the comparison result, and the risk assessment process of the grid operation status is updated according to the judgment result, wherein: When Q>Q0, the risk assessment module determines that the grid load characteristic type is the grid load peak period, and the risk assessment module updates the risk assessment process of the grid operation status, and calculates the environmental index HJ according to the temperature W, humidity S, electric field strength X and noise Z, and sets HJ=0.2W+0.2S+0.2X+0.4Z, and compares the environmental index HJ with the preset environmental index HJ0, and judges the grid operation environment according to the comparison result, and updates the risk assessment process of the grid operation status according to the judgment result, wherein: If HJ≥HJ0, the risk assessment module determines that the power grid operation environment is up to standard, and the risk assessment module does not update the risk assessment process of the power grid operation status; If HJ<HJ0, the risk assessment module determines that the power grid operating environment is not up to standard. The risk assessment module optimizes the parameters according to the power grid load. Adjust the grid load Q and set , the adjusted grid load is Q1, set Q1= Q, and update the risk assessment process of the grid operation status according to the adjusted grid load; When Q≤Q0, the risk assessment module determines that the grid load characteristic type is a grid load off-peak period, and the risk assessment module does not update the risk assessment process of the grid operation status.

[0014] On the other hand, the present invention also provides a power grid fault simulation training method based on extended reality, the method comprising: Step S1, collecting power grid fault simulation data of each power grid device, and preprocessing the power grid fault simulation data to obtain actual power grid fault simulation data; Step S2, integrating the actual power grid fault simulation data to obtain actual power grid fault integrated data, and constructing a power grid fault simulation scenario according to the actual power grid fault integrated data; Step S3, performing simulated monitoring on the fault information of each power grid device according to the power grid fault simulation scenario to obtain simulated monitoring results, acquiring simulated operation data according to the simulated monitoring results, outputting virtual reality operation instructions according to the simulated operation data, and conducting training interaction for power grid operation and maintenance personnel according to the virtual reality operation instructions and the fault information of each power grid device; Step S4, performing risk assessment on the grid operation status according to the fault information, and updating the risk assessment process of the grid operation status according to the grid load.

[0015] Compared with the prior art, the beneficial effects of the present invention are that the system can efficiently collect the grid fault simulation data of each grid device through the data acquisition module, and provide an accurate data source for subsequent data processing and analysis. The system can preprocess the collected grid fault simulation data through the data preprocessing module to obtain accurate actual grid fault simulation data. The system can construct an accurate grid fault simulation scenario according to the actual grid fault simulation data through the fault scenario construction module, simulate various grid fault conditions, and help grid operation and maintenance personnel deal with actual grid faults. The system can simulate and monitor the fault information of the grid equipment according to the grid fault simulation scenario through the simulation training interaction module, and output virtual reality operation instructions, and conduct training interaction with the grid operation and maintenance personnel, so as to intuitively understand the operating principle of the grid equipment and improve the fault handling ability of the grid operation and maintenance personnel. The system can perform risk assessment on the grid operation status according to the fault information through the risk assessment module, and dynamically adjust the risk assessment process according to the grid load, so as to ensure the accuracy and reliability of the risk assessment of the grid operation status.

[0016] In particular, the data acquisition module can acquire power grid fault simulation data through the power grid fault simulation data acquisition device, thereby ensuring the accuracy of the power grid fault simulation.

[0017] In particular, the data preprocessing module can accurately identify abnormal values ​​in power grid fault simulation data, improve data quality, and enhance data availability and accuracy.

[0018] In particular, the fault scenario construction module can accurately evaluate the correlation between the power grid equipment fault simulation data and the actual fault situation, thereby improving the accuracy of evaluating power grid faults.

[0019] In particular, the fault scenario construction module constructs a power grid fault simulation scenario according to a power grid fault simulation scenario construction model, thereby improving the accuracy of constructing the power grid fault simulation scenario.

[0020] In particular, the simulation training interactive module can accurately simulate and monitor the fault information of power grid equipment, and mark the faults through data visualization methods, thereby effectively improving the efficiency and accuracy of power grid fault simulation training.

[0021] In particular, the simulation training interaction module can accurately identify the user's simulation operation and generate corresponding virtual reality operation instructions according to the standard simulation operation data-virtual reality operation instruction template, thereby improving the efficiency and accuracy of training.

[0022] In particular, the simulation training interaction module can calculate the similarity between virtual reality operation instructions and power grid equipment fault information, intelligently filter and sort the fault information, and conduct targeted training interactions for power grid operation and maintenance personnel based on the fault handling solution with the highest similarity, thereby improving the efficiency of training power grid operation and maintenance personnel.

[0023] In particular, the risk assessment module collects voltage data and current data in the fault information, constructs a time series and a distance matrix, and calculates a cumulative distance matrix and an optimal matching path, thereby improving the accuracy of risk assessment of the power grid operation status.

[0024] In particular, the risk assessment module is used to intelligently determine the type of grid load characteristics, thereby ensuring the accuracy and efficiency of grid operation risk assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 This is a schematic diagram of the structure of the power grid fault simulation training system based on extended reality in this embodiment; Figure 2 Schematic diagram of the flow of the power grid fault simulation training method based on extended reality in this embodiment. DETAILED DESCRIPTION

[0026] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0027] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0028] It should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0029] See also Figure 1 As shown, it is a structural diagram of a power grid fault simulation training system based on extended reality in this embodiment, and the system includes: A data acquisition module is used to collect power grid fault simulation data of each power grid device; A data preprocessing module, used for preprocessing the power grid fault simulation data to obtain actual power grid fault simulation data, the data preprocessing module is connected to the data acquisition module; A fault scenario construction module, used to integrate the actual power grid fault simulation data to obtain actual power grid fault integrated data, and also used to construct a power grid fault simulation scenario according to the actual power grid fault integrated data, the fault scenario construction module is connected to the data preprocessing module; A simulation training interaction module, used to simulate monitoring of the fault information of each power grid device according to the power grid fault simulation scenario to obtain a simulation monitoring result, and also used to obtain simulation operation data according to the simulation monitoring result, and output virtual reality operation instructions according to the simulation operation data, and also used to perform training interaction for power grid operation and maintenance personnel according to the virtual reality operation instructions and the fault information of each power grid device, and the simulation training interaction module is connected to the fault scenario construction module; The risk assessment module is used to perform risk assessment on the grid operation status according to the fault information, and is also used to update the risk assessment process of the grid operation status according to the grid load. The risk assessment module is connected to the simulation training interaction module.

[0030] Specifically, the system is arranged in a control terminal based on extended reality power grid fault simulation training, and constructs a power grid fault simulation scenario through actual power grid fault simulation data to realize simulation training of fault diagnosis and processing, and combined with power grid topology information, it can improve the fault diagnosis and processing capabilities of power grid operation and maintenance personnel, and accurately evaluate the risk of power grid operation status through the fault information and power grid load, and provide strong guarantee for the safe operation of the power grid. Among them, the system can efficiently collect power grid fault simulation data of each power grid equipment through the data acquisition module, and provide an accurate data source for subsequent data processing and analysis. The system can pre-process the collected power grid fault simulation data through the data preprocessing module, so as to obtain accurate actual power grid fault simulation data. The system can construct accurate power grid fault simulation scenarios according to actual power grid fault simulation data through the fault scenario construction module, simulate various power grid fault conditions, and help power grid operation and maintenance personnel deal with actual power grid faults. The system can simulate and monitor the fault information of power grid equipment according to the power grid fault simulation scenario through the simulation training interaction module, and output virtual reality operation instructions, and conduct training interaction with power grid operation and maintenance personnel, so as to intuitively understand the operating principles of power grid equipment and improve the fault handling capabilities of power grid operation and maintenance personnel. The system can conduct risk assessment of the power grid operation status according to the fault information through the risk assessment module, and dynamically adjust the risk assessment process according to the power grid load, so as to ensure the accuracy and reliability of the risk assessment of the power grid operation status.

[0031] Specifically, the data acquisition module collects the power grid fault simulation data of each power grid device in real time through the power grid fault simulation data acquisition device.

[0032] Specifically, the power grid equipment refers to various equipment in the power system, the power grid fault simulation data refers to a data set collected in real time by a power grid fault simulation data acquisition device, including power grid operation data, the power grid operation data refers to the operation data during the overall operation of the power grid, including real-time electrical parameters and operation status data, the real-time electrical parameters refer to the real-time electrical measurement values ​​of various power grid equipment in the power grid, such as voltage and current, the operation status data refers to the operation status information of various power grid equipment, such as protection action information and operating temperature of power grid equipment, the power grid fault simulation data acquisition device refers to a device for real-time collection of power grid fault simulation data, including a power grid equipment management system and an electrical parameter sensor, the power grid equipment management system refers to a system for collecting power grid equipment data and historical power grid fault data for interfacing with the power grid fault simulation training system, the power grid equipment data refers to the performance data of various equipment in the power grid, including basic information of the power grid equipment, topological connection information between power grid equipment and characteristic curves of the power grid equipment, the basic information of the power grid equipment refers to various equipment in the power grid The basic attributes and status information of the power grid equipment, such as the equipment name, rated parameters and current operating status, the topological connection information between the power grid equipment refers to the connection relationship and connection mode between the various equipment in the power grid, such as the connection sequence of various equipment in the substation and the start and end nodes of the transmission line, the characteristic curve of the power grid equipment refers to the curve that describes the performance of the power grid equipment as the parameters change, such as the current-voltage curve in the transformer, the historical power grid fault data refers to the data record of fault events that occurred in the power grid in the past, including the fault type, the fault impact range and the fault processing record, the fault type refers to the specific type of fault that occurred in the power grid, such as short circuit fault, overload fault and equipment fault, the fault impact range refers to the range of the power grid area affected after the fault occurs, such as power outages for users within the power supply range of a line caused by a line fault, the fault processing record refers to the record of the process of diagnosing, locating and repairing the fault, such as the operation steps taken by maintenance personnel, and the electrical parameter sensor refers to a device for measuring power grid operation data, including a voltage sensor, a current sensor, a temperature sensor and a position sensor.

[0033] Specifically, the data acquisition module can acquire power grid fault simulation data through the power grid fault simulation data acquisition device to ensure the accuracy of the power grid fault simulation.

[0034] Specifically, the data preprocessing module performs outlier detection on the power grid fault simulation data of each power grid device according to the data anomaly detection algorithm to obtain corresponding data anomaly values, and processes the data anomaly values ​​according to the data anomaly value processing scheme corresponding to the power grid fault simulation data to obtain corresponding anomaly value processing results, and performs data conversion on the anomaly value processing results according to the data conversion scheme to obtain corresponding actual power grid fault simulation data.

[0035] Specifically, the data anomaly detection algorithm refers to an algorithm for detecting whether there are outliers in the data. This embodiment does not limit the specific implementation method of the data anomaly detection algorithm. Those skilled in the art can freely set it according to the actual situation, and only need to meet the needs of outlier detection on the power grid fault simulation data of each power grid device. For example, it can be set to perform outlier detection on each power grid fault simulation data through an isolation forest algorithm. The data outlier value refers to the value obtained by performing outlier detection on each power grid fault simulation data according to the data anomaly detection algorithm. The data outlier value processing scheme refers to a strategy for processing the data outliers. This embodiment does not limit the specific implementation method of the data outlier value processing scheme. Those skilled in the art can freely set it according to the actual situation, and only need to meet the needs of performing outlier detection on the power grid fault simulation data of each power grid device. It is only necessary to meet the demand for processing the data outliers, such as being able to be set to process the data outliers through the 3-sigma method, the outlier processing result refers to the result obtained by processing the data outliers according to the data outlier processing scheme corresponding to each power grid fault simulation data, the data conversion scheme refers to a strategy for converting data, this embodiment does not limit the specific implementation of the data conversion scheme, and technical personnel in this field can freely set it according to actual conditions, and it is only necessary to meet the demand for data conversion of the outlier processing results, such as being able to be set to convert the outlier processing results through the Z-score method, and the actual power grid fault simulation data refers to the data obtained by converting the outlier processing results according to the data conversion scheme.

[0036] Specifically, the data preprocessing module can accurately identify abnormal values ​​in power grid fault simulation data, improve data quality, and enhance data availability and accuracy.

[0037] Specifically, the fault scenario construction module performs correlation analysis on the actual power grid fault simulation data corresponding to each power grid device with the power grid device data and the historical power grid fault data according to the correlation analysis algorithm to obtain the actual correlation ZX, and compares the actual correlation ZX with the preset correlation ZX0, performs integration judgment on the actual power grid fault simulation data of the power grid device according to the comparison result, and integrates the actual power grid fault simulation data of the power grid device according to the judgment result, wherein: When ZX≥ZX0, the fault scenario construction module determines to integrate the actual power grid fault simulation data of the power grid device, and integrates the actual power grid fault simulation data according to the default data integration rule of the power grid device to obtain the actual power grid fault integrated data; When ZX<ZX0, the fault scenario construction module determines not to integrate the actual power grid fault simulation data of the power grid device.

[0038] Specifically, the correlation analysis algorithm refers to an algorithm for evaluating the degree of correlation between the actual power grid fault simulation data corresponding to each power grid device and the power grid equipment data and historical power grid fault data. This embodiment does not limit the specific implementation method of the correlation analysis algorithm. Technical personnel in this field can freely set it according to actual conditions. It only needs to meet the need of correlation analysis between the actual power grid fault simulation data corresponding to each power grid device and the power grid equipment data and historical power grid fault data. For example, it can be set to perform correlation analysis on the actual power grid fault simulation data corresponding to each power grid device and the power grid equipment data and historical power grid fault data through the Pearson correlation coefficient method. The actual correlation ZX refers to the correlation between the actual power grid fault simulation data corresponding to each power grid device and the power grid equipment data and historical power grid fault data according to the correlation analysis algorithm. The result obtained by analysis, the preset correlation degree ZX0 refers to the preset value compared with the actual correlation degree ZX, for example 0.8, the data integration rule refers to the preset integration rule of each power grid device when ZX<ZX0, the present embodiment does not limit the specific implementation mode of the data integration rule, technical personnel in this field can freely set it according to the actual situation, and only need to meet the demand for integrating the actual power grid fault simulation data, such as it can be set to integrate the basic information of each power grid device with the actual power grid fault simulation data of the power grid device, and integrate the historical power grid fault data of each power grid device with the actual power grid fault simulation data of the power grid device, the actual power grid fault integrated data refers to the data obtained by integrating the actual power grid fault simulation data corresponding to the power grid device according to the default data integration rule of each power grid device.

[0039] Specifically, the fault scenario construction module can accurately evaluate the correlation between the power grid equipment fault simulation data and the actual fault situation, thereby improving the accuracy of evaluating power grid faults.

[0040] Specifically, the fault scenario construction module trains the convolutional neural network model according to a preset power grid fault simulation scenario construction data set, outputs the convolutional neural network model that meets the preset accuracy as a power grid fault simulation scenario construction model, and inputs the actual power grid fault integrated data into the power grid fault simulation scenario construction model for construction to obtain a power grid fault simulation scenario.

[0041] Specifically, the power grid fault simulation scenario construction model refers to a model that meets the preset accuracy rate by training the convolutional neural network model according to the preset power grid fault simulation scenario construction data set. The preset power grid fault simulation scenario construction data set refers to a preset data set for training the convolutional neural network model in the form of historical power grid fault simulation scenario construction information-power grid fault simulation scenario. This embodiment does not limit the way in which the convolutional neural network model is trained. For example, it can be set to divide 75% of the preset power grid fault simulation scenario construction data set into a model training set and 25% into a model test set, input the model training set into the convolutional neural network model for training, and input the model test set into the trained convolutional neural network model, optimize and iterate the parameters in the convolutional neural network model until the output result of the model test set of the convolutional neural network model meets the preset accuracy rate, and output the convolutional neural network model as a power grid fault simulation scenario construction model. The preset accuracy rate refers to a preset value reflecting the accuracy rate of the training of the convolutional neural network model, such as 95%. The power grid fault simulation scenario refers to a simulation scenario obtained by inputting the actual power grid fault integrated data into the power grid fault simulation scenario construction model.

[0042] Specifically, the fault scenario construction module constructs a power grid fault simulation scenario according to a power grid fault simulation scenario construction model, thereby improving the accuracy of constructing the power grid fault simulation scenario.

[0043] Specifically, the simulation training interaction module obtains the fault type characteristic data G_i of each power grid device and the operating status data Y_i corresponding to each power grid device according to the power grid fault simulation scenario, and calculates the power grid fault index FZ_i corresponding to each power grid device according to the fault type characteristic data G_i and the operating status data Y_i, respectively, and sets FZ_i=a_i×G_i+b_i×Y_i, a_i represents a coefficient for adjusting the fault type characteristic data G_i, b_i represents a coefficient for adjusting the operating status data Y_i, and compares the power grid fault index FZ_i with the preset power grid fault index FZ0_i corresponding to each power grid device, and simulates monitoring of the fault information of each power grid device according to the comparison result, wherein: When FZ_i≥FZ0_i, the simulation training interaction module simulates monitoring of the fault information of the power grid equipment, and performs fault labeling on the fault information of the power grid equipment according to the preset power grid fault index corresponding to the power grid equipment, obtains the fault labeling result, and simulates monitoring of the fault labeling result through a data visualization method; When FZ_i<FZ0_i, the simulation training interaction module does not perform simulation monitoring on the fault information of the power grid equipment.

[0044] Specifically, the fault type characteristic data G_i refers to data describing the fault type and characteristics of the power grid equipment, the operating status data Y_i refers to various status parameters of the power grid equipment during operation, the preset power grid fault index FZ0_i refers to the fault judgment threshold set for each power grid equipment, for example, for a high-voltage circuit breaker, the preset power grid fault index FZ0_i is set to 100, the data visualization method refers to a method for intuitively displaying the operating status and fault information of the power grid equipment, this embodiment does not limit the data visualization method, and those skilled in the art can freely set it according to actual conditions, and only need to meet the needs of simulating monitoring the fault labeling results, such as setting it to display the current voltage value, current value and comparison with the rated value of the power grid equipment through a chart, this embodiment does not limit the implementation method of fault labeling, and those skilled in the art can freely set it according to actual conditions, and only need to meet the needs of fault labeling the fault information of the power grid equipment, such as setting it to perform fault labeling of the fault information of each power grid equipment in the form of text labeling, the fault information refers to the information of each power grid equipment in an abnormal state, and the fault labeling result refers to the result obtained by fault labeling the fault information of the power grid equipment according to the preset power grid fault index corresponding to the power grid equipment.

[0045] Specifically, the simulation training interactive module can accurately simulate and monitor the fault information of power grid equipment, and mark the faults through data visualization methods, thereby effectively improving the efficiency and accuracy of power grid fault simulation training.

[0046] Specifically, the simulation training interaction module identifies the simulation monitoring results according to the simulation operation data identification model to obtain simulation operation data, and compares the simulation operation data with the standard simulation operation data-virtual reality operation instruction template, and outputs the virtual reality operation instruction according to the comparison result, wherein: When there is preset standardized simulation operation data consistent with the simulation operation data in the standard simulation operation data-virtual reality operation instruction template, the preset virtual reality operation instruction corresponding to the preset standardized simulation operation data is output as the virtual reality operation instruction; When there is no preset standardized simulation operation data consistent with the simulation operation data in the standard simulation operation data-virtual reality operation instruction template, the virtual reality operation instruction is not output.

[0047] Specifically, the simulation operation data recognition model refers to a deep learning model that takes the characteristic graph of historical simulation monitoring results as input and the simulation operation data recognition result as output. This embodiment does not limit the construction method of the simulation operation data recognition model. Those skilled in the art can freely set it according to actual conditions, as long as the need for identifying the simulation monitoring results is met. For example, the simulation operation data recognition model can be set to be a convolutional neural network model. The simulation operation data refers to the data obtained by identifying the simulation monitoring results according to the simulation operation data recognition model. The standard simulation operation data-virtual reality operation instruction template refers to a predefined data template for comparison with the simulation operation data to identify the corresponding virtual reality operation instruction, including preset standardized simulation operation data and preset virtual reality operation instructions. The preset standardized simulation operation data refers to preset standardized simulation operation data for identifying virtual reality operation instructions. The preset virtual reality operation instruction refers to a preset virtual reality operation instruction corresponding to the preset standardized simulation operation data.

[0048] Specifically, the simulation training interaction module can accurately identify the user's simulation operation and generate corresponding virtual reality operation instructions according to the standard simulation operation data-virtual reality operation instruction template, thereby improving the efficiency and accuracy of training.

[0049] Specifically, the simulation training interaction module calculates the similarity between the virtual reality operation instructions and the fault information of each power grid device according to the similarity measurement method, obtains the actual similarity A1 corresponding to each power grid device, and compares the actual similarity A1 with the preset similarity A0 of each power grid device, and performs training interaction for the power grid operation and maintenance personnel according to the comparison results, wherein: When A1<A0, the simulation training interaction module does not perform training interaction for the power grid operation and maintenance personnel; When A1≥A0, the simulation training interaction module sorts the actual similarity between the fault information of each power grid device satisfying A1≥A0 and the virtual reality operation instruction, and performs training interaction for the power grid operation and maintenance personnel according to the preset power grid fault handling solution corresponding to the largest actual similarity.

[0050] Specifically, the similarity measurement method refers to a method for calculating the similarity between the virtual reality operation instruction and the fault information of each power grid device. This embodiment does not limit the specific implementation method of the similarity measurement method. Those skilled in the art can freely set it according to the actual situation, and only need to meet the need for similarity calculation between the virtual reality operation instruction and the fault information of each power grid device. For example, it can be set to calculate the similarity between the virtual reality operation instruction and the fault information of each power grid device through the Manhattan distance method. The actual similarity A1 corresponding to each power grid device refers to the result obtained by calculating the similarity between the virtual reality operation instruction and the fault information of each power grid device according to the similarity measurement method. The preset similarity A0 of each power grid device refers to a preset value for comparison with the actual similarity A1 corresponding to each power grid device, such as 0.95. The preset power grid fault handling scheme refers to a measure pre-formulated for the power grid fault of each power grid device. This embodiment does not limit the specific implementation method of the preset power grid fault handling scheme. Those skilled in the art can freely set it according to the actual situation, and only need to meet the need for training and interaction with power grid operation and maintenance personnel. For example, it can be set to prompt the fault handling scheme according to the fault information of each power grid device and the actual operation of the power grid operation and maintenance personnel.

[0051] Specifically, the simulation training interaction module can calculate the similarity between virtual reality operation instructions and power grid equipment fault information, intelligently filter and sort the fault information, and conduct targeted training interactions for power grid operation and maintenance personnel based on the fault handling solution with the highest similarity, thereby improving the efficiency of training for power grid operation and maintenance personnel.

[0052] Specifically, the risk assessment module collects the voltage data and current data in the fault information according to a preset collection time period, and sets the collected voltage data as a first time series. , set the collected current data as the second time series ,in represents the voltage value at time m, Represents the current value at time n and creates a distance matrix Store the first time series To the second time series The distance between the points in ,in , , represents the voltage value at time k, represents the current value at time l; Build a The same cumulative distance matrix ,set up , and according to Cumulative distance matrix Calculate and use the cumulative distance matrix The best matching path Calculate and set , where P represents the backtracking path and r represents the cumulative distance matrix The index in and the best matching path The best matching path Compare and conduct risk assessment on the power grid operation status based on the comparison results, including: when > When , the risk assessment module assesses the power grid operation state as a high-risk operation state; when = When , the risk assessment module assesses the power grid operation state as a medium-risk operation state; when < When the risk assessment module assesses the power grid operation state as a low-risk operation state.

[0053] Specifically, the voltage data refers to the voltage corresponding to each power grid device when a fault occurs, the current data refers to the current corresponding to each power grid device when a fault occurs, the first time series refers to a sequence formed by arranging the collected voltage data in chronological order, the second time series refers to a sequence formed by arranging the collected current data in chronological order, the cumulative distance matrix refers to a data matrix used to store the cumulative distances between points in the first time series and the second time series, the optimal matching path refers to a path found in the cumulative distance matrix so that the distance from the first time series to the second time series is the smallest, and the preset optimal matching path refers to a preset standard for comparison with the optimal matching path.

[0054] Specifically, the risk assessment module collects voltage data and current data in the fault information, constructs a time series and a distance matrix, and calculates a cumulative distance matrix and an optimal matching path, thereby improving the accuracy of risk assessment of the power grid operation status.

[0055] Specifically, the risk assessment module calculates the grid load Q according to the unit power consumption index P and the unit quantity N, and sets The grid load Q is compared with the preset grid load Q0, the grid load characteristic type is judged according to the comparison result, and the risk assessment process of the grid operation status is updated according to the judgment result, wherein: When Q>Q0, the risk assessment module determines that the grid load characteristic type is the grid load peak period, and the risk assessment module updates the risk assessment process of the grid operation status, and calculates the environmental index HJ according to the temperature W, humidity S, electric field strength X and noise Z, and sets HJ=0.2W+0.2S+0.2X+0.4Z, and compares the environmental index HJ with the preset environmental index HJ0, and judges the grid operation environment according to the comparison result, and updates the risk assessment process of the grid operation status according to the judgment result, wherein: If HJ≥HJ0, the risk assessment module determines that the power grid operation environment is up to standard, and the risk assessment module does not update the risk assessment process of the power grid operation status; If HJ<HJ0, the risk assessment module determines that the power grid operating environment is not up to standard. The risk assessment module optimizes the parameters according to the power grid load. Adjust the grid load Q and set , the adjusted grid load is Q1, set Q1= Q, and update the risk assessment process of the grid operation status according to the adjusted grid load; When Q≤Q0, the risk assessment module determines that the grid load characteristic type is a grid load off-peak period, and the risk assessment module does not update the risk assessment process of the grid operation status.

[0056] Specifically, the unit power consumption index P refers to the electric energy consumed per unit time, the unit quantity N refers to the unit quantity used to calculate the power grid load, the preset power grid load refers to the preset value compared with the power grid load Q, such as 10000kWh, the power grid load characteristic type refers to the type divided according to the size and change trend of the power grid load, the risk assessment process refers to the process of risk analysis and assessment of the power grid operation status, the preset environmental index HJ0 refers to the preset value compared with the environmental index HJ, such as 0.7, the power grid operation environment refers to the environmental conditions under which the power grid operates, and the power grid load optimization parameters It refers to the parameters used to adjust the power grid load. The adjusted power grid load is the power grid load obtained by adjusting the power grid load according to the power grid load optimization parameters.

[0057] Specifically, the risk assessment module is used to intelligently determine the type of grid load characteristics, thereby ensuring the accuracy and efficiency of grid operation risk assessment.

[0058] See also Figure 2 As shown, it is a flow chart of the power grid fault simulation training method based on extended reality in this embodiment, and the method includes: Step S1, collecting power grid fault simulation data of each power grid device, and preprocessing the power grid fault simulation data to obtain actual power grid fault simulation data; Step S2, integrating the actual power grid fault simulation data to obtain actual power grid fault integrated data, and constructing a power grid fault simulation scenario according to the actual power grid fault integrated data; Step S3, performing simulated monitoring on the fault information of each power grid device according to the power grid fault simulation scenario to obtain simulated monitoring results, acquiring simulated operation data according to the simulated monitoring results, outputting virtual reality operation instructions according to the simulated operation data, and conducting training interaction for power grid operation and maintenance personnel according to the virtual reality operation instructions and the fault information of each power grid device; Step S4, performing risk assessment on the grid operation status according to the fault information, and updating the risk assessment process of the grid operation status according to the grid load.

[0059] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A power grid fault simulation training system based on extended reality, characterized in that: The system comprises: A data acquisition module is used to collect power grid fault simulation data of each power grid device; A data preprocessing module, used for preprocessing the power grid fault simulation data to obtain actual power grid fault simulation data; A fault scenario construction module, used to integrate the actual power grid fault simulation data to obtain actual power grid fault integrated data, and also used to construct a power grid fault simulation scenario according to the actual power grid fault integrated data; A simulation training interaction module is used to simulate monitoring of the fault information of each power grid device according to the power grid fault simulation scenario to obtain a simulation monitoring result, and is also used to obtain simulation operation data according to the simulation monitoring result, and output virtual reality operation instructions according to the simulation operation data, and is also used to perform training interaction for power grid operation and maintenance personnel according to the virtual reality operation instructions and the fault information of each power grid device; The risk assessment module is used to perform risk assessment on the operation status of the power grid according to the fault information, and is also used to update the risk assessment process of the operation status of the power grid according to the load of the power grid.

2. The power grid fault simulation training system based on extended reality according to claim 1, characterized in that: The data preprocessing module performs outlier detection on the power grid fault simulation data of each power grid device according to the data anomaly detection algorithm to obtain corresponding data anomaly values, and processes the data anomaly values ​​according to the data anomaly value processing scheme corresponding to the power grid fault simulation data to obtain corresponding anomaly value processing results, and performs data conversion on the anomaly value processing results according to the data conversion scheme to obtain corresponding actual power grid fault simulation data.

3. The power grid fault simulation training system based on extended reality according to claim 1, characterized in that: The fault scenario construction module performs correlation analysis on the actual power grid fault simulation data corresponding to each power grid device with the power grid device data and the historical power grid fault data according to the correlation analysis algorithm to obtain the actual correlation ZX, and compares the actual correlation ZX with the preset correlation ZX0, performs integration judgment on the actual power grid fault simulation data of the power grid device according to the comparison result, and integrates the actual power grid fault simulation data of the power grid device according to the judgment result, wherein: When ZX≥ZX0, the fault scenario construction module determines to integrate the actual power grid fault simulation data of the power grid device, and integrates the actual power grid fault simulation data according to the default data integration rule of the power grid device to obtain the actual power grid fault integrated data; When ZX<ZX0, the fault scenario construction module determines not to integrate the actual power grid fault simulation data of the power grid device.

4. The power grid fault simulation training system based on extended reality according to claim 3, characterized in that: The fault scenario construction module trains the convolutional neural network model according to a preset power grid fault simulation scenario construction data set, outputs the convolutional neural network model that meets the preset accuracy as a power grid fault simulation scenario construction model, and inputs the actual power grid fault integrated data into the power grid fault simulation scenario construction model for construction to obtain a power grid fault simulation scenario.

5. The power grid fault simulation training system based on extended reality according to claim 1, characterized in that: The simulation training interaction module obtains the fault type characteristic data G_i of each power grid device and the operating status data Y_i corresponding to each power grid device according to the power grid fault simulation scenario, and calculates the power grid fault index FZ_i corresponding to each power grid device according to the fault type characteristic data G_i and the operating status data Y_i, respectively, and sets FZ_i=a_i×G_i+b_i×Y_i, where a_i represents a coefficient for adjusting the fault type characteristic data G_i, and b_i represents a coefficient for adjusting the operating status data Y_i, and compares the power grid fault index FZ_i with the preset power grid fault index FZ0_i corresponding to each power grid device, and simulates monitoring of the fault information of each power grid device according to the comparison result, wherein: When FZ_i≥FZ0_i, the simulation training interaction module simulates monitoring of the fault information of the power grid equipment, and performs fault labeling on the fault information of the power grid equipment according to the preset power grid fault index corresponding to the power grid equipment, obtains the fault labeling result, and simulates monitoring of the fault labeling result through a data visualization method; When FZ_i<FZ0_i, the simulation training interaction module does not perform simulation monitoring on the fault information of the power grid equipment.

6. The power grid fault simulation training system based on extended reality according to claim 5, characterized in that: The simulation training interaction module identifies the simulation monitoring results according to the simulation operation data identification model to obtain simulation operation data, and compares the simulation operation data with the standard simulation operation data-virtual reality operation instruction template, and outputs the virtual reality operation instruction according to the comparison result, wherein: When there is preset standardized simulation operation data consistent with the simulation operation data in the standard simulation operation data-virtual reality operation instruction template, the preset virtual reality operation instruction corresponding to the preset standardized simulation operation data is output as the virtual reality operation instruction; When there is no preset standardized simulation operation data consistent with the simulation operation data in the standard simulation operation data-virtual reality operation instruction template, the virtual reality operation instruction is not output.

7. The power grid fault simulation training system based on extended reality according to claim 6, characterized in that: The simulation training interaction module calculates the similarity between the virtual reality operation instructions and the fault information of each power grid device according to the similarity measurement method, obtains the actual similarity A1 corresponding to each power grid device, and compares the actual similarity A1 with the preset similarity A0 of each power grid device, and performs training interaction for the power grid operation and maintenance personnel according to the comparison result, wherein: When A1<A0, the simulation training interaction module does not perform training interaction for the power grid operation and maintenance personnel; When A1≥A0, the simulation training interaction module sorts the actual similarity between the fault information of each power grid device satisfying A1≥A0 and the virtual reality operation instruction, and performs training interaction for the power grid operation and maintenance personnel according to the preset power grid fault handling solution corresponding to the largest actual similarity.

8. The power grid fault simulation training system based on extended reality according to claim 1, characterized in that: The risk assessment module collects the voltage data and current data in the fault information according to a preset collection time period, and sets the collected voltage data as a first time series , set the collected current data as the second time series ,in represents the voltage value at time m, Represents the current value at time n and creates a distance matrix Store the first time series To the second time series The distance between the points in ,in , , represents the voltage value at time k, represents the current value at time l; Build a The same cumulative distance matrix ,set up , and according to Cumulative distance matrix Calculate and use the cumulative distance matrix The best matching path Calculate and set , where P represents the backtracking path and r represents the cumulative distance matrix The index in and the best matching path The best matching path with the preset Compare and conduct risk assessment on the power grid operation status based on the comparison results, including: when > When , the risk assessment module assesses the power grid operation state as a high-risk operation state; when = When , the risk assessment module assesses the power grid operation state as a medium-risk operation state; when < When the risk assessment module assesses the power grid operation state as a low-risk operation state.

9. The power grid fault simulation training system based on extended reality according to claim 8, characterized in that: The risk assessment module calculates the grid load Q according to the unit power consumption index P and the unit quantity N, and sets The grid load Q is compared with the preset grid load Q0, the grid load characteristic type is judged according to the comparison result, and the risk assessment process of the grid operation status is updated according to the judgment result, wherein: When Q>Q0, the risk assessment module determines that the grid load characteristic type is the grid load peak period, and the risk assessment module updates the risk assessment process of the grid operation status, and calculates the environmental index HJ according to the temperature W, humidity S, electric field strength X and noise Z, and sets HJ=0.2W+0.2S+0.2X+0.4Z, and compares the environmental index HJ with the preset environmental index HJ0, and judges the grid operation environment according to the comparison result, and updates the risk assessment process of the grid operation status according to the judgment result, wherein: If HJ≥HJ0, the risk assessment module determines that the power grid operation environment is up to standard, and the risk assessment module does not update the risk assessment process of the power grid operation status; If HJ<HJ0, the risk assessment module determines that the power grid operating environment is not up to standard. The risk assessment module optimizes the parameters according to the power grid load. Adjust the grid load Q and set , the adjusted grid load is Q1, set Q1= Q, and update the risk assessment process of the grid operation status according to the adjusted grid load; When Q≤Q0, the risk assessment module determines that the grid load characteristic type is a grid load off-peak period, and the risk assessment module does not update the risk assessment process of the grid operation status.

10. A method for applying the extended reality-based power grid fault simulation training system according to any one of claims 1 to 9, the method comprising: Step S1, collecting power grid fault simulation data of each power grid device, and preprocessing the power grid fault simulation data to obtain actual power grid fault simulation data; Step S2, integrating the actual power grid fault simulation data to obtain actual power grid fault integrated data, and constructing a power grid fault simulation scenario according to the actual power grid fault integrated data; Step S3, performing simulated monitoring on the fault information of each power grid device according to the power grid fault simulation scenario to obtain simulated monitoring results, acquiring simulated operation data according to the simulated monitoring results, outputting virtual reality operation instructions according to the simulated operation data, and conducting training interaction for power grid operation and maintenance personnel according to the virtual reality operation instructions and the fault information of each power grid device; Step S4, performing risk assessment on the grid operation status according to the fault information, and updating the risk assessment process of the grid operation status according to the grid load.

Images